Skip to main content

Python SDK for HyperCLI - GPU orchestration and HyperAgent API

Project description

HyperCLI SDK

Python SDK for HyperCLI - GPU orchestration API.

Installation

pip install hypercli-sdk

Setup

Set your API key:

export HYPER_API_KEY=your_api_key

Or create ~/.hypercli/config:

HYPER_API_KEY=your_api_key

Or pass directly:

client = HyperCLI(api_key="your_api_key")

Usage

from hypercli import HyperCLI

client = HyperCLI()

# Check balance
balance = client.billing.balance()
print(f"Balance: ${balance.total:.2f}")
print(f"Rewards: ${balance.rewards:.2f}")

# List transactions
for tx in client.billing.transactions(limit=10):
    print(f"{tx.transaction_type}: ${tx.amount_usd:.4f}")

# Create a job
job = client.jobs.create(
    image="nvidia/cuda:12.0",
    command="python train.py",
    gpu_type="l40s",
    gpu_count=1,
)
print(f"Job ID: {job.job_id}")
print(f"State: {job.state}")

# List jobs
for job in client.jobs.list():
    print(f"{job.job_id}: {job.state}")

# Get job details
job = client.jobs.get("job_id")

# Get job logs
logs = client.jobs.logs("job_id")

# Get GPU metrics
metrics = client.jobs.metrics("job_id")
for gpu in metrics.gpus:
    print(f"GPU {gpu.index}: {gpu.utilization}% util, {gpu.temperature}°C")

# Cancel a job
client.jobs.cancel("job_id")

# Extend runtime
client.jobs.extend("job_id", runtime=7200)

# Get user info
user = client.user.get()
print(f"User: {user.email}")

HyperAgent API

Use client.agent for discovery and plan metadata, and point the OpenAI SDK at the HyperClaw inference base URL for chat completions:

from hypercli import HyperCLI
from openai import OpenAI

sdk = HyperCLI(api_key="hyper_api_key", agent_api_key="sk-agent")
plans = sdk.agent.plans()

client = OpenAI(
    api_key="your_hyperagent_api_key",
    base_url="https://api.hypercli.com/v1"
)

response = client.chat.completions.create(
    model="deepseek-v3.1",
    messages=[{"role": "user", "content": "Hello!"}]
)

Error Handling

from hypercli import HyperCLI, APIError

client = HyperCLI()

try:
    job = client.jobs.get("invalid_id")
except APIError as e:
    print(f"Error {e.status_code}: {e.detail}")

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hypercli_sdk-2026.4.7.tar.gz (95.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

hypercli_sdk-2026.4.7-py3-none-any.whl (78.0 kB view details)

Uploaded Python 3

File details

Details for the file hypercli_sdk-2026.4.7.tar.gz.

File metadata

  • Download URL: hypercli_sdk-2026.4.7.tar.gz
  • Upload date:
  • Size: 95.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for hypercli_sdk-2026.4.7.tar.gz
Algorithm Hash digest
SHA256 79e89b9ccbdac4e54a806a75af9044104d9cfee05fc561037e3f54eae3639380
MD5 8767d023e7a6f09ec32b99060e63253b
BLAKE2b-256 1a9192c8f65ea273787c48e89e4054958e85da632bfb953d0b1a776709db86d2

See more details on using hashes here.

File details

Details for the file hypercli_sdk-2026.4.7-py3-none-any.whl.

File metadata

File hashes

Hashes for hypercli_sdk-2026.4.7-py3-none-any.whl
Algorithm Hash digest
SHA256 8e182b3b486f90b97bb0414f2aaccbaffb443cbe16f0380883d6be8619e13495
MD5 4f2ec0eb9d0e2c807b7f012978447659
BLAKE2b-256 832656bb3e01e38fca3c71505a5d945ad2de09c85f10db8482de0294e5716037

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page